Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Pairwise LLM-judge evaluation research benchmarks · SOTA2 Research

Pairwise LLM-judge evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Arena-Hard and WildBench (combined)

57.7Win Rate

12

Feb 26, 2026

Popular datasets

Arena-Hard and WildBench

Follow for updates

Join SOTA2 Contact